When Claws Remember but Do Not Tell: Stealthy Memory Injection in Persistent Personal Agents

• URL: http://arxiv.org/abs/2607.05189v1
• Date: Mon, 06 Jul 2026 15:08:58 GMT
• Title: When Claws Remember but Do Not Tell: Stealthy Memory Injection in Persistent Personal Agents
• Abstract summary: We study the threat as stealth memory injection, in which a remote black-box delivers a single email payload that must induce the agent to poisoned memory.<n>We propose MemGhost, a one-shot payload generation framework.<n>Across 56 held-out test cases, MemGhost achieves 87.5% end-to-end success on OpenClaw with GPT-5.4 and 71.4% on Claude Code SDK with Sonnet 4.6.
• Score: 55.87577638514179
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Persistent personal agents combine long-term memory with access to users' external environments, enabling personalized foreground assistance and proactive background execution. This integration also creates a new path to compromise: untrusted external content can be silently written into persistent memory and later reused as trusted state. We study this threat as stealth memory injection, in which a remote black-box adversary delivers a single email payload that must induce the agent to write poisoned memory, stay hidden in the agent's response to the user, and affect future behavior. We introduce WhisperBench, a 108-case benchmark spanning five risk categories and both fact and preference poisoning. Built on a real IMAP/SMTP workflow and an authentic email agent skill, it enables full-cycle evaluation of stealth memory injection attacks. To enable this black-box attack under single-email delivery and without runtime feedback, we propose MemGhost, a one-shot payload generation framework. MemGhost uses an environment proxy to emulate persistent-agent execution and an objective proxy to convert memory adoption and conversational stealth into dense rubric-based rewards, then trains the attacker policy with supervised fine-tuning and reinforcement learning. Across 56 held-out test cases, MemGhost achieves 87.5% end-to-end success on OpenClaw with GPT-5.4 and 71.4% on Claude Code SDK with Sonnet 4.6. It also transfers across personal-agent architectures (NanoClaw and Hermes Agent) and memory backends (filesystem and vector-based Mem0), and remains effective against input-level, model-level, and system-level defenses. These results suggest that persistent memory can turn ordinary external processing into a practical pathway for long-term agent compromise.

Related papers

• When Malicious Instructions Persist: Persistent Memory Poisoning Attack on Harness-Based Agents [17.320527773100732]
  We propose PMPA, a Persistent Memory Poisoning Attack against harness-based agents.<n> PMPA embeds malicious instructions into benign external sources and induces the victim agent to write them into persistent memory.<n>Across all settings, PMPA achieves average Injection Success Rate (ISR) and Cross-session Attack Success Rate (C-ASR) of 73.7%/ 55.5% on OpenClaw and 66.9%/ 81.7% on Claude Code.
  arXiv  Detail & Related papers  (2026-09-12T11:27:53Z)
• Bad Memory: Evaluating Prompt Injection Risks from Memory in Agentic Systems [11.238342775567856]
  We study prompt injection attacks in memory-based agentic systems using a sandboxed synthetic workspace.<n>Our results show that although it is difficult to make an agent overwrite its own memory files using untrusted external content, payloads already planted in those files can successfully attack current and future sessions.
  arXiv  Detail & Related papers  (2026-07-16T06:13:48Z)
• Understanding and Evaluating Claw-like Agent Security Through a Computer-Systems Lens [65.53494487819053]
  Claw-like AI agents (e.g., OpenClaw) are always-on processes with persistent access to credentials, files, tools, and external services.<n>We adopt a computer-system analogy: treating a Claw-like agent as an agentic computer system whose gateway runtime plays an OS-like mediation role.<n>We develop SafeClawArena, a benchmark of 406 adversarial tasks across four attack surfaces.
  arXiv  Detail & Related papers  (2026-06-29T18:00:45Z)
• Capable but Careless: Do Computer-Use Agents Follow Contextual Integrity? [54.701199583505144]
  Cross-application access creates a privacy risk that has been largely overlooked.<n>We introduce AgentCIBench, an evaluation harness that turns this risk into executable, deterministically scored scenarios.<n>We evaluate 15 frontier agents and find a surprisingly high failure rate.
  arXiv  Detail & Related papers  (2026-06-22T11:36:58Z)
• MemVenom: Triggered Poisoning of Multimodal Memories in Web Agents [74.64265314956441]
  We propose a unified black-box attack framework that poisons graph-structured external memory with coordinated text-image evidence.<n>MemVenom achieves strong end-to-end attack success with minimal impact on benign performance, reaching up to 99.15% on GPT-5-family web agents.
  arXiv  Detail & Related papers  (2026-06-09T11:53:25Z)
• Hijacking Agent Memory: Stealthy Trojan Attacks Through Conversational Interaction [3.809725488301918]
  Large language model (LLM) agents increasingly leverage long term memory to support persistent and autonomous task execution.<n>Existing memory poisoning attacks assume that injected content can be stored directly in memory, overlooking the selective extraction and rewriting stages.<n>Mechanistic analysis indicates that the attack exploits embedding-space anisotropy and shifts attention patterns.
  arXiv  Detail & Related papers  (2026-05-28T14:02:00Z)
• Trojan Hippo: Weaponizing Agent Memory for Data Exfiltration [33.8989871605613]
  Trojan Hippo is a class of persistent memory attacks that operates in a more realistic threat model than prior memory poisoning work.<n>We evaluate four memory-system defenses inspired by basic security principles, finding they substantially reduce attack success rates.<n>Because of this substantial security-utility tradeoff, the effective real-world deployment of defenses remains an open challenge.
  arXiv  Detail & Related papers  (2026-05-03T17:07:20Z)
• Zombie Agents: Persistent Control of Self-Evolving LLM Agents via Self-Reinforcing Injections [57.64370755825839]
  Self-evolving agents update their internal state across sessions, often by writing and reusing long-term memory.<n>We study this risk and formalize a persistent attack we call a Zombie Agent.<n>We present a black-box attack framework that uses only indirect exposure through attacker-controlled web content.
  arXiv  Detail & Related papers  (2026-02-17T15:28:24Z)
• AgentSys: Secure and Dynamic LLM Agents Through Explicit Hierarchical Memory Management [47.49917373646469]
  Existing defenses treat bloated memory as given and focus on remaining resilient.<n>We present AgentSys, a framework that defends against indirect prompt injection through explicit memory management.
  arXiv  Detail & Related papers  (2026-02-07T06:28:51Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.